Information Extraction Based on Multi-turn Question Answering for Analyzing Korean Research Trends

Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the popularities of the topics or codes over time.Although it is simple and effective,the taxonomies are difficult to manage because new technologies are introduced rapidly.Therefore,recent studies exploit deep learning to extract pre-defined targets such as problems and solutions.Based on the recent advances in question answering(QA)using deep learning,we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports.With the previous research,we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction(IE)for sentence-level benchmark dataset.After investigating the characteristics of Korean R&D,we propose a model to deal with multiple and repeated appearances of targets in the reports.Accordingly,we propose a model that includes an algorithm with two novel modules and a prompt.A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge.We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.

Semantic Information Extraction from Multi-Corpora Using Deep Learning

Information extraction plays a vital role in natural language processing,to extract named entities and events from unstructured data.Due to the exponential data growth in the agricultural sector,extracting significant information has become a challenging task.Though existing deep learningbased techniques have been applied in smart agriculture for crop cultivation,crop disease detection,weed removal,and yield production,still it is difficult to find the semantics between extracted information due to unswerving effects of weather,soil,pest,and fertilizer data.This paper consists of two parts.An initial phase,which proposes a data preprocessing technique for removal of ambiguity in input corpora,and the second phase proposes a novel deep learning-based long short-term memory with rectification in Adam optimizer andmultilayer perceptron to find agricultural-based named entity recognition,events,and relations between them.The proposed algorithm has been trained and tested on four input corpora i.e.,agriculture,weather,soil,and pest&fertilizers.The experimental results have been compared with existing techniques and itwas observed that the proposed algorithm outperformsWeighted-SOM,LSTM+RAO,PLR-DBN,KNN,and Na飗e Bayes on standard parameters like accuracy,sensitivity,and specificity.

Supporting Information Extraction from Visual Documents

Visual Information Extraction (VIE) is a technique that enables users to perform information extraction from visual documents driven by the visual appearance and the spatial relations occurring among the elements in the document. In particular, the extractions are expressed through a query language similar to the well known SQL. To further reduce the human effort in the extraction task, in this paper we present a fully formalized assistance mechanism that helps users in the interactive formulation of the queries.

A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction

This paper focuses on term-status pair extraction from medical dialogues(MD-TSPE),which is essential in diagnosis dia-logue systems and the automatic scribe of electronic medical records(EMRs).In the past few years,works on MD-TSPE have attracted increasing research attention,especially after the remarkable progress made by generative methods.However,these generative methods output a whole sequence consisting of term-status pairs in one stage and ignore integrating prior knowledge,which demands a deeper un-derstanding to model the relationship between terms and infer the status of each term.This paper presents a knowledge-enhanced two-stage generative framework(KTGF)to address the above challenges.Using task-specific prompts,we employ a single model to com-plete the MD-TSPE through two phases in a unified generative form:We generate all terms the first and then generate the status of each generated term.In this way,the relationship between terms can be learned more effectively from the sequence containing only terms in the first phase,and our designed knowledge-enhanced prompt in the second phase can leverage the category and status candidates of the generated term for status generation.Furthermore,our proposed special status"not mentioned"makes more terms available and en-riches the training data in the second phase,which is critical in the low-resource setting.The experiments on the Chunyu and CMDD datasets show that the proposed method achieves superior results compared to the state-of-the-art models in the full training and low-re-sourcesettings.

Research on Extraction Method of Surface Information Based on Multi-Feature Combination Such as Fractal Texture

Because of the developed economy and lush vegetation in southern China, the following obstacles or difficulties exist in remote sensing land surface classification: 1) Diverse surface composition types;2) Undulating terrains;3) Small fragmented land;4) Indistinguishable shadows of surface objects. It is our top priority to clarify how to use the concept of big data (Data mining technology) and various new technologies and methods to make complex surface remote sensing information extraction technology develop in the direction of automation, refinement and intelligence. In order to achieve the above research objectives, the paper takes the Gaofen-2 satellite data produced in China as the data source, and takes the complex surface remote sensing information extraction technology as the research object, and intelligently analyzes the remote sensing information of complex surface on the basis of completing the data collection and preprocessing. The specific extraction methods are as follows: 1) extraction research on fractal texture features of Brownian motion;2) extraction research on color features;3) extraction research on vegetation index;4) research on vectors and corresponding classification. In this paper, fractal texture features, color features, vegetation features and spectral features of remote sensing images are combined to form a combination feature vector, which improves the dimension of features, and the feature vector improves the difference of remote sensing features, and it is more conducive to the classification of remote sensing features, and thus it improves the classification accuracy of remote sensing images. It is suitable for remote sensing information extraction of complex surface in southern China. This method can be extended to complex surface area in the future.

A Joint Entity Relation Extraction Model Based on Relation Semantic Template Automatically Constructed

The joint entity relation extraction model which integrates the semantic information of relation is favored by relevant researchers because of its effectiveness in solving the overlapping of entities,and the method of defining the semantic template of relation manually is particularly prominent in the extraction effect because it can obtain the deep semantic information of relation.However,this method has some problems,such as relying on expert experience and poor portability.Inspired by the rule-based entity relation extraction method,this paper proposes a joint entity relation extraction model based on a relation semantic template automatically constructed,which is abbreviated as RSTAC.This model refines the extraction rules of relation semantic templates from relation corpus through dependency parsing and realizes the automatic construction of relation semantic templates.Based on the relation semantic template,the process of relation classification and triplet extraction is constrained,and finally,the entity relation triplet is obtained.The experimental results on the three major Chinese datasets of DuIE,SanWen,and FinRE showthat the RSTAC model successfully obtains rich deep semantics of relation,improves the extraction effect of entity relation triples,and the F1 scores are increased by an average of 0.96% compared with classical joint extraction models such as CasRel,TPLinker,and RFBFN.

Word Embedding Bootstrapped Deep Active Learning Method to Information Extraction on Chinese Electronic Medical Record

Electronic medical record (EMR) containing rich biomedical information has a great potential in disease diagnosis and biomedical research. However, the EMR information is usually in the form of unstructured text, which increases the use cost and hinders its applications. In this work, an effective named entity recognition (NER) method is presented for information extraction on Chinese EMR, which is achieved by word embedding bootstrapped deep active learning to promote the acquisition of medical information from Chinese EMR and to release its value. In this work, deep active learning of bi-directional long short-term memory followed by conditional random field (Bi-LSTM+CRF) is used to capture the characteristics of different information from labeled corpus, and the word embedding models of contiguous bag of words and skip-gram are combined in the above model to respectively capture the text feature of Chinese EMR from unlabeled corpus. To evaluate the performance of above method, the tasks of NER on Chinese EMR with “medical history” content were used. Experimental results show that the word embedding bootstrapped deep active learning method using unlabeled medical corpus can achieve a better performance compared with other models.

SciCN:A Scientific Dataset for Chinese Named Entity Recognition

Named entity recognition(NER)is a fundamental task of information extraction(IE),and it has attracted considerable research attention in recent years.The abundant annotated English NER datasets have significantly promoted the NER research in the English field.By contrast,much fewer efforts are made to the Chinese NER research,especially in the scientific domain,due to the scarcity of Chinese NER datasets.To alleviate this problem,we present aChinese scientificNER dataset–SciCN,which contains entity annotations of titles and abstracts derived from 3,500 scientific papers.We manually annotate a total of 62,059 entities,and these entities are classified into six types.Compared to English scientific NER datasets,SciCN has a larger scale and is more diverse,for it not only contains more paper abstracts but these abstracts are derived from more research fields.To investigate the properties of SciCN and provide baselines for future research,we adapt a number of previous state-of-theart Chinese NER models to evaluate SciCN.Experimental results show that SciCN is more challenging than other Chinese NER datasets.In addition,previous studies have proven the effectiveness of using lexicons to enhance Chinese NER models.Motivated by this fact,we provide a scientific domain-specific lexicon.Validation results demonstrate that our lexicon delivers better performance gains than lexicons of other domains.We hope that the SciCN dataset and the lexicon will enable us to benchmark the NER task regarding the Chinese scientific domain and make progress for future research.The dataset and lexicon are available at:https://github.com/yangjingla/SciCN.git.

Quality oriented multimode processes monitoring based on a novel hierarchical common and specific structure with different order information

Due to higher demands on product diversity,flexible shift between productions of different products in one equipment becomes a popular solution,resulting in existence of multiple operation modes in a single process.In order to handle such multi-mode process,a novel double-layer structure is proposed and the original data are decomposed into common and specific characteristics according to the relationship between variables among each mode.In addition,both low and high order information are considered in each layer.The common and specific information within each mode can be captured and separated into several subspaces according to the different order information.The performance of the proposed method is further validated through a numerical example and the Tennessee Eastman(TE)benchmark.Compared with previous methods,superiority of the proposed method is validated by the better monitoring results.

A Combinatorial Optimized Knapsack Linear Space for Information Retrieval

Key information extraction can reduce the dimensional effects while evaluating the correct preferences of users during semantic data analysis.Currently,the classifiers are used to maximize the performance of web-page recommendation in terms of precision and satisfaction.The recent method disambiguates contextual sentiment using conceptual prediction with robustness,however the conceptual prediction method is not able to yield the optimal solution.Context-dependent terms are primarily evaluated by constructing linear space of context features,presuming that if the terms come together in certain consumerrelated reviews,they are semantically reliant.Moreover,the more frequently they coexist,the greater the semantic dependency is.However,the influence of the terms that coexist with each other can be part of the frequency of the terms of their semantic dependence,as they are non-integrative and their individual meaning cannot be derived.In this work,we consider the strength of a term and the influence of a term as a combinatorial optimization,called Combinatorial Optimized Linear Space Knapsack for Information Retrieval(COLSK-IR).The COLSK-IR is considered as a knapsack problem with the total weight being the“term influence”or“influence of term”and the total value being the“term frequency”or“frequency of term”for semantic data analysis.The method,by which the term influence and the term frequency are considered to identify the optimal solutions,is called combinatorial optimizations.Thus,we choose the knapsack for performing an integer programming problem and perform multiple experiments using the linear space through combinatorial optimization to identify the possible optimum solutions.It is evident from our experimental results that the COLSK-IR provides better results than previous methods to detect strongly dependent snippets with minimum ambiguity that are related to inter-sentential context during semantic data analysis.

Combing Type-Aware Attention and Graph Convolutional Networks for Event Detection

Event detection(ED)is aimed at detecting event occurrences and categorizing them.This task has been previously solved via recognition and classification of event triggers(ETs),which are defined as the phrase or word most clearly expressing event occurrence.Thus,current approaches require both annotated triggers as well as event types in training data.Nevertheless,triggers are non-essential in ED,and it is time-wasting for annotators to identify the“most clearly”word from a sentence,particularly in longer sentences.To decrease manual effort,we evaluate event detectionwithout triggers.We propose a novel framework that combines Type-aware Attention and Graph Convolutional Networks(TA-GCN)for event detection.Specifically,the task is identified as a multi-label classification problem.We first encode the input sentence using a novel type-aware neural network with attention mechanisms.Then,a Graph Convolutional Networks(GCN)-based multilabel classification model is exploited for event detection.Experimental results demonstrate the effectiveness.

An Adaptive Vision Navigation Algorithm in Agricultural IoT System for Smart Agricultural Robots

As the agricultural internet of things(IoT)technology has evolved,smart agricultural robots needs to have both flexibility and adaptability when moving in complex field environments.In this paper,we propose the concept of a vision-based navigation system for the agricultural IoT and a binocular vision navigation algorithm for smart agricultural robots,which can fuse the edge contour and the height information of rows of crop in images to extract the navigation parameters.First,the speeded-up robust feature(SURF)extracting and matching algorithm is used to obtain featuring point pairs from the green crop row images observed by the binocular parallel vision system.Then the confidence density image is constructed by integrating the enhanced elevation image and the corresponding binarized crop row image,where the edge contour and the height information of crop row are fused to extract the navigation parameters(θ,d)based on the model of a smart agricultural robot.Finally,the five navigation network instruction sets are designed based on the navigation angleθand the lateral distance d,which represent the basic movements for a certain type of smart agricultural robot working in a field.Simulated experimental results in the laboratory show that the algorithm proposed in this study is effective with small turning errors and low standard deviations,and can provide a valuable reference for the further practical application of binocular vision navigation systems in smart agricultural robots in the agricultural IoT system.

Enhancement of Sentiment Analysis Using Clause and Discourse Connectives

The sentiment of a text depends on the clausal structure of the sentence and the connectives’discourse arguments.In this work,the clause boundary,discourse argument,and syntactic and semantic information of the sentence are used to assign the text’s sentiment.The clause boundaries identify the span of the text,and the discourse connectives identify the arguments.Since the lexicon-based analysis of traditional sentiment analysis gives the wrong sentiment of the sentence,a deeper-level semantic analysis is required for the correct analysis of sentiments.Hence,in this study,explicit connectives in Malayalam are considered to identify the discourse arguments.A supervised method,conditional random fields,is used to identify the clause boundary and discourse arguments.For the study,1,000 sentiment sentences from Malayalam documents were analyzed.Experimental results show that the discourse structure integration considerably improves sentiment analysis performance from the baseline system.

Time-Aware PolarisX: Auto-Growing Knowledge Graph

A knowledge graph is a structured graph in which data obtained from multiple sources are standardized to acquire and integrate human knowledge.Research is being actively conducted to cover a wide variety of knowledge,as it can be applied to applications that help humans.However,existing researches are constructing knowledge graphs without the time information that knowledge implies.Knowledge stored without time information becomes outdated over time,and in the future,the possibility of knowledge being false or meaningful changes is excluded.As a result,they can’t reect information that changes dynamically,and they can’t accept information that has newly emerged.To solve this problem,this paper proposes Time-Aware PolarisX,an automatically extended knowledge graph including time information.TimeAware PolarisX constructed a BERT model with a relation extractor and an ensemble NER model including a time tag with an entity extractor to extract knowledge consisting of subject,relation,and object from unstructured text.Through two application experiments,it shows that the proposed system overcomes the limitations of existing systems that do not consider time information when applied to an application such as a chatbot.Also,we verify that the accuracy of the extraction model is improved through a comparative experiment with the existing model.

LRV: A Tool for Academic Text Visualization to Support theLiterature Review Process

Text visualization is concerned with the representation of text in a graphicalform to facilitate comprehension of large textual data. Its aim is to improve the ability tounderstand and utilize the wealth of text-based information available. An essential task inany scientific research is the study and review of previous works in the specified domain,a process that is referred to as the literature survey process. This process involves theidentification of prior work and evaluating its relevance to the research question. With theenormous number of published studies available online in digital form, this becomes acumbersome task for the researcher. This paper presents the design and implementationof a tool that aims to facilitate this process by identifying relevant work and suggestingclusters of articles by conceptual modeling, thus providing different options that enablethe researcher to visualize a large number of articles in a graphical easy-to-analyze form.The tool helps the researcher in analyzing and synthesizing the literature and building aconceptual understanding of the designated research area. The evaluation of the toolshows that researchers have found it useful and that it supported the process of relevantwork analysis given a specific research question, and 70% of the evaluators of the toolfound it very useful.

Contextual Text Mining Framework for Unstructured Textual Judicial Corpora through Ontologies

Digitalization has changed the way of information processing, and newtechniques of legal data processing are evolving. Text mining helps to analyze andsearch different court cases available in the form of digital text documents toextract case reasoning and related data. This sort of case processing helps professionals and researchers to refer the previous case with more accuracy in reducedtime. The rapid development of judicial ontologies seems to deliver interestingproblem solving to legal knowledge formalization. Mining context informationthrough ontologies from corpora is a challenging and interesting field. Thisresearch paper presents a three tier contextual text mining framework throughontologies for judicial corpora. This framework comprises on the judicial corpus,text mining processing resources and ontologies for mining contextual text fromcorpora to make text and data mining more reliable and fast. A top-down ontologyconstruction approach has been adopted in this paper. The judicial corpus hasbeen selected with a sufficient dataset to process and evaluate the results.The experimental results and evaluations show significant improvements incomparison with the available techniques.

A Prior Information Enhanced Extraction Framework for Document-level Financial Event Extraction

Document-level financial event extraction(DFEE) is the task of detecting events and extracting the corresponding event arguments in financial documents, which plays an important role in information extraction in the financial domain. This task is challenging as the financial documents are generally long text and event arguments of one event may be scattered in different sentences. To address this issue, we proposed a novel Prior Information Enhanced Extraction framework(PIEE) for DFEE, leveraging prior information from both event types and pre-trained language models. Specifically, PIEE consists of three components: event detection, event argument extraction, and event table filling. In event detection, we identify the event type. Then, the event type is explicitly used for event argument extraction. Meanwhile, the implicit information within language models also provides considerable cues for event arguments localization. Finally, all the event arguments are filled in an event table by a set of predefined heuristic rules. To demonstrate the effectiveness of our proposed framework, we participated in the share task of CCKS2020 Task 4-2: Documentlevel Event Arguments Extraction. On both Leaderboard A and Leaderboard B, PIEE took the first place and significantly outperformed the other systems.

Let Some Unforeseen Knowledge Emerge from Heterogeneous Documents

Data production and exchange on the Web grows at a frenetic speed. Such uncontrolled and exponential growth pushes for new researches in the area of information extraction as it is of great interest and can be obtained by processing data gathered from several heterogeneous sources. While some extracted facts can be correct at the origin, it is not possible to verify that correlations among the mare always true (e.g., they can relate to different points of time). We need systems smart enough to separate signal from noise and hence extract real value from this abundance of content accessible on the Web. In order to extract information from heterogeneous sources, we are involved into the entire process of identifying specific facts/events of interest. We propose a gluing architecture, driving the whole knowledge acquisition process, from data acquisition from external heterogeneous resources to their exploitation for RDF trip lification to support reasoning tasks. Once the extraction process is completed, a dedicated reasoner can infer new knowledge as a result of the reasoning process defined by the end user by means of specific inference rules over both extracted information and the background knowledge. The end user is supported in this context with an intelligent interface allowing to visualize either specific data/concepts, or all information inferred by applying deductive reasoning over a collection of data.

Construction and Application of Knowledge Graph for Quality and Safety Supervision of Transportation Engineering

Knowledge graph technology play a more and more important role in various fields of industry and academia.This paper firstly introduces the general framework of the knowledge graph construction,which includes three stages:information extraction,knowledge fusion and knowledge processing.In order to improve the efficiency of quality and safety supervision of transportation engineering construction,this paper constructs a knowledge graph by acquiring multi-sources heterogeneous data from supervision of transportation engineering quality and safety.It employs a bottom-up construction strategy and some natural language processing methods to solve the problems of the knowledge extraction for transportation engineering construction.We use the entity relation extraction method to extract the entity triples from the multi-sources heterogeneous data,and then employ knowledge inference to complete the edges in the constructed knowledge graph,finally perform quality evaluation to add the valid triples to the knowledge graph for updating.Subgraph matching technology is also exploited to retrieve the constructed knowledge graph for efficiently acquiring the useful knowledge about the quality and safety of transportation engineering projects.The results show that the constructed knowledge graph provides a practical and valuable tool for the quality and safety supervision of transportation engineering construction.

Annotation and Joint Extraction of Scientific Entities and Relationships in NSFC Project Texts

Aiming at the lack of classification and good standard corpus in the task of joint entity and relationship extraction in the current Chinese academic field, this paper builds a dataset in management science that can be used for joint entity and relationship extraction, and establishes a deep learning model to extract entity and relationship information from scientific texts. With the definition of entity and relation classification, we build a Chinese scientific text corpus dataset based on the abstract texts of projects funded by the National Natural Science Foundation of China(NSFC) in 2018–2019. By combining the word2vec features with the clue word feature which is a kind of special style in scientific documents, we establish a joint entity relationship extraction model based on the Bi LSTM-CNN-CRF model for scientific information extraction. The dataset we constructed contains 13060 entities(not duplicated) and 9728 entity relation labels. In terms of entity prediction effect, the accuracy rate of the constructed model reaches 69.15%, the recall rate reaches 61.03%, and the F1 value reaches 64.83%. In terms of relationship prediction effect, the accuracy rate is higher than that of entity prediction, which reflects the effectiveness of the input mixed features and the integration of local features with CNN layer in the model.